Assessment of the current and emerging criteria for the histopathological classification of lung neuroendocrine tumours in the lungNENomics project.

BACKGROUND: Six thoracic pathologists reviewed 259 lung neuroendocrine tumours (LNETs) from the lungNENomics project, with 171 of them having associated survival data. This cohort presents a unique opportunity to assess the strengths and limitations of current World Health Organization (WHO) classification criteria and to evaluate the utility of emerging markers. PATIENTS AND METHODS: Patients were diagnosed based on the 2021 WHO criteria, with atypical carcinoids (ACs) defined by the presence of focal necrosis and/or 2-10 mitoses per 2 mm2. We investigated two markers of tumour proliferation: the Ki-67 index and phospho-histone H3 (PHH3) protein expression, quantified by pathologists and automatically via deep learning. Additionally, an unsupervised deep learning algorithm was trained to uncover previously unnoticed morphological features with diagnostic value. RESULTS: The accuracy in distinguishing typical from ACs is hampered by interobserver variability in mitotic counting and the limitations of morphological criteria in identifying aggressive cases. Our study reveals that different Ki-67 cut-offs can categorise LNETs similarly to current WHO criteria. Counting mitoses in PHH3+ areas does not improve diagnosis, while providing a similar prognostic value to the current criteria. With the advantage of being time efficient, automated assessment of these markers leads to similar conclusions. Lastly, state-of-the-art deep learning modelling does not uncover undisclosed morphological features with diagnostic value. CONCLUSIONS: This study suggests that the mitotic criteria can be complemented by manual or automated assessment of Ki-67 or PHH3 protein expression, but these markers do not significantly improve the prognostic value of the current classification, as the AC group remains highly unspecific for aggressive cases. Therefore, we may have exhausted the potential of morphological features in classifying and prognosticating LNETs. Our study suggests that it might be time to shift the research focus towards investigating molecular markers that could contribute to a more clinically relevant morpho-molecular classification.

Precise and automated lung cancer cell classification using deep neural network with multiscale features and model distillation.

Lung diseases globally impose a significant pathological burden and mortality rate, particularly the differential diagnosis between adenocarcinoma, squamous cell carcinoma, and small cell lung carcinoma, which is paramount in determining optimal treatment strategies and improving clinical prognoses. Faced with the challenge of improving diagnostic precision and stability, this study has developed an innovative deep learning-based model. This model employs a Feature Pyramid Network (FPN) and Squeeze-and-Excitation (SE) modules combined with a Residual Network (ResNet18), to enhance the processing capabilities for complex images and conduct multi-scale analysis of each channel's importance in classifying lung cancer. Moreover, the performance of the model is further enhanced by employing knowledge distillation from larger teacher models to more compact student models. Subjected to rigorous five-fold cross-validation, our model outperforms existing models on all performance metrics, exhibiting exceptional diagnostic accuracy. Ablation studies on various model components have verified that each addition effectively improves model performance, achieving an average accuracy of 98.84% and a Matthews Correlation Coefficient (MCC) of 98.83%. Collectively, the results indicate that our model significantly improves the accuracy of disease diagnosis, providing physicians with more precise clinical decision-making support.

The Classification of VOCs Based on Sensor Images Using a Lightweight Neural Network for Lung Cancer Diagnosis.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection, which detects the patient's exhaled VOCs, combined with sensor arrays of convolutional neural network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, the low accuracy, high-complexity computation and large number of parameters make the CNN algorithms difficult to transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models, such as EfficientNet, LTNet has fewer parameters (32 K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than the scores of the six existing models, and it also offers the shortest training (844.38 s and 584.67 s) and inference times (23 s and 14 s) in the same validation sets. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

[Pulmonary neuroendocrine tumors : Current review]. / Pulmonale neuroendokrine Tumoren : Aktuelle Übersicht.

CLINICAL ISSUE: Neuroendocrine neoplasms of the lung are a heterogenous tumor group. The pathological classification comprises diffuse idiopathic pulmonary neuroendocrine cell hyperplasia, classic neuroendocrine tumors, and neuroendocrine carcinoma. Classic neuroendocrine tumors include typical and atypical carcinoid tumors. DIAGNOSTIC WORK-UP: Imaging plays an important role in diagnosis and can help in identifying the tumor biology. Overall, this tumor group is rare, comprising less than 2% of all thoracic tumors. PRACTICAL RECOMMENDATIONS: In the current review, the various tumors are presented and important aspects regarding pathological classification, imaging modalities, and treatment are described.

Optimizing double-layered convolutional neural networks for efficient lung cancer classification through hyperparameter optimization and advanced image pre-processing techniques.

Lung cancer remains a leading cause of cancer-related mortality globally, with prognosis significantly dependent on early-stage detection. Traditional diagnostic methods, though effective, often face challenges regarding accuracy, early detection, and scalability, being invasive, time-consuming, and prone to ambiguous interpretations. This study proposes an advanced machine learning model designed to enhance lung cancer stage classification using CT scan images, aiming to overcome these limitations by offering a faster, non-invasive, and reliable diagnostic tool. Utilizing the IQ-OTHNCCD lung cancer dataset, comprising CT scans from various stages of lung cancer and healthy individuals, we performed extensive preprocessing including resizing, normalization, and Gaussian blurring. A Convolutional Neural Network (CNN) was then trained on this preprocessed data, and class imbalance was addressed using Synthetic Minority Over-sampling Technique (SMOTE). The model's performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and ROC curve analysis. The results demonstrated a classification accuracy of 99.64%, with precision, recall, and F1-score values exceeding 98% across all categories. SMOTE significantly enhanced the model's ability to classify underrepresented classes, contributing to the robustness of the diagnostic tool. These findings underscore the potential of machine learning in transforming lung cancer diagnostics, providing high accuracy in stage classification, which could facilitate early detection and tailored treatment strategies, ultimately improving patient outcomes.

Classification of lung cancer subtypes on CT images with synthetic pathological priors.

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), positive predictive value (PPV) and F1-score.

Invasion and Grading of Pulmonary Non-Mucinous Adenocarcinoma.

Lung adenocarcinoma staging and grading were recently updated to reflect the link between histologic growth patterns and outcomes. The lepidic growth pattern is regarded as "in-situ," whereas all other patterns are regarded as invasive, though with stratification. Solid, micropapillary, and complex glandular patterns are associated with worse prognosis than papillary and acinar patterns. These recent changes have improved prognostic stratification. However, multiple pitfalls exist in measuring invasive size and in classifying lung adenocarcinoma growth patterns. Awareness of these limitations and recommended practices will help the pathology community achieve consistent prognostic performance and potentially contribute to improved patient management.

ML3CNet: Non-local means-assisted automatic framework for lung cancer subtypes classification using histopathological images.

BACKGROUND AND OBJECTIVE: Lung cancer (LC) has a high fatality rate that continuously affects human lives all over the world. Early detection of LC prolongs human life and helps to prevent the disease. Histopathological inspection is a common method to diagnose LC. Visual inspection of histopathological diagnosis necessitates more inspection time, and the decision depends on the subjective perception of clinicians. Usually, machine learning techniques mostly depend on traditional feature extraction which is labor-intensive and may not be appropriate for enormous data. In this work, a convolutional neural network (CNN)-based architecture is proposed for the more effective classification of lung tissue subtypes using histopathological images. METHODS: Authors have utilized the first-time nonlocal mean (NLM) filter to suppress the effect of noise from histopathological images. NLM filter efficiently eliminated noise while preserving the edges of images. Then, the obtained denoised images are given as input to the proposed multi-headed lung cancer classification convolutional neural network (ML3CNet). Furthermore, the model quantization technique is utilized to reduce the size of the proposed model for the storage of the data. Reduction in model size requires less memory and speeds up data processing. RESULTS: The effectiveness of the proposed model is compared with the other existing state-of-the-art methods. The proposed ML3CNet achieved an average classification accuracy of 99.72%, sensitivity of 99.66%, precision of 99.64%, specificity of 99.84%, F-1 score of 0.9965, and area under the curve of 0.9978. The quantized accuracy of 98.92% is attained by the proposed model. To validate the applicability of the proposed ML3CNet, it has also been tested on the colon cancer dataset. CONCLUSION: The findings reveal that the proposed approach can be beneficial to automatically classify LC subtypes that might assist healthcare workers in making decisions more precisely. The proposed model can be implemented on the hardware using Raspberry Pi for practical realization.

Correlation between Radiological Characteristics, PET-CT and Histological Subtypes of Primary Lung Adenocarcinoma-A 102 Case Series Analysis.

Background and Objectives: Lung cancer is the second most common form of cancer in the world for both men and women as well as the most common cause of cancer-related deaths worldwide. The aim of this study is to summarize the radiological characteristics between primary lung adenocarcinoma subtypes and to correlate them with FDG uptake on PET-CT. Materials and Methods: This retrospective study included 102 patients with pathohistologically confirmed lung adenocarcinoma. A PET-CT examination was performed on some of the patients and the values of SUVmax were also correlated with the histological and morphological characteristics of the masses in the lungs. Results: The results of this analysis showed that the mean size of AIS-MIA (adenocarcinoma in situ and minimally invasive adenocarcinoma) cancer was significantly lower than for all other cancer types, while the mean size of the acinar cancer was smaller than in the solid type of cancer. Metastases were significantly more frequent in solid adenocarcinoma than in acinar, lepidic, and AIS-MIA cancer subtypes. The maximum standardized FDG uptake was significantly lower in AIS-MIA than in all other cancer types and in the acinar predominant subtype compared to solid cancer. Papillary predominant adenocarcinoma had higher odds of developing contralateral lymph node involvement compared to other types. Solid adenocarcinoma was associated with higher odds of having metastases and with higher SUVmax. AIS-MIA was associated with lower odds of one unit increase in tumor size and ipsilateral lymph node involvement. Conclusions: The correlation between histopathological and radiological findings is crucial for accurate diagnosis and staging. By integrating both sets of data, clinicians can enhance diagnostic accuracy and determine the optimal treatment plan.

A multi-instance tumor subtype classification method for small PET datasets using RA-DL attention module guided deep feature extraction with radiomics features.

BACKGROUND: Positron emission tomography (PET) is extensively employed for diagnosing and staging various tumors, including liver cancer, lung cancer, and lymphoma. Accurate subtype classification of tumors plays a crucial role in formulating effective treatment plans for patients. Notably, lymphoma comprises subtypes like diffuse large B-cell lymphoma and Hodgkin's lymphoma, while lung cancer encompasses adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. Similarly, liver cancer consists of subtypes such as cholangiocarcinoma and hepatocellular carcinoma. Consequently, the subtype classification of tumors based on PET images holds immense clinical significance. However, in clinical practice, the number of cases available for each subtype is often limited and imbalanced. Therefore, the primary challenge lies in achieving precise subtype classification using a small dataset. METHOD: This paper presents a novel approach for tumor subtype classification in small datasets using RA-DL (Radiomics-DeepLearning) attention. To address the limited sample size, Support Vector Machines (SVM) is employed as the classifier for tumor subtypes instead of deep learning methods. Emphasizing the importance of texture information in tumor subtype recognition, radiomics features are extracted from the tumor regions during the feature extraction stage. These features are compressed using an autoencoder to reduce redundancy. In addition to radiomics features, deep features are also extracted from the tumors to leverage the feature extraction capabilities of deep learning. In contrast to existing methods, our proposed approach utilizes the RA-DL-Attention mechanism to guide the deep network in extracting complementary deep features that enhance the expressive capacity of the final features while minimizing redundancy. To address the challenges of limited and imbalanced data, our method avoids using classification labels during deep feature extraction and instead incorporates 2D Region of Interest (ROI) segmentation and image reconstruction as auxiliary tasks. Subsequently, all lesion features of a single patient are aggregated into a feature vector using a multi-instance aggregation layer. RESULT: Validation experiments were conducted on three PET datasets, specifically the liver cancer dataset, lung cancer dataset, and lymphoma dataset. In the context of lung cancer, our proposed method achieved impressive performance with Area Under Curve (AUC) values of 0.82, 0.84, and 0.83 for the three-classification task. For the binary classification task of lymphoma, our method demonstrated notable results with AUC values of 0.95 and 0.75. Moreover, in the binary classification task of liver tumor, our method exhibited promising performance with AUC values of 0.84 and 0.86. CONCLUSION: The experimental results clearly indicate that our proposed method outperforms alternative approaches significantly. Through the extraction of complementary radiomics features and deep features, our method achieves a substantial improvement in tumor subtype classification performance using small PET datasets.

A dual data stream hybrid neural network for classifying pathological images of lung adenocarcinoma.

Lung cancer has seriously threatened human health due to its high lethality and morbidity. Lung adenocarcinoma, in particular, is one of the most common subtypes of lung cancer. Pathological diagnosis is regarded as the gold standard for cancer diagnosis. However, the traditional manual screening of lung cancer pathology images is time consuming and error prone. Computer-aided diagnostic systems have emerged to solve this problem. Current research methods are unable to fully exploit the beneficial features inherent within patches, and they are characterized by high model complexity and significant computational effort. In this study, a deep learning framework called Multi-Scale Network (MSNet) is proposed for the automatic detection of lung adenocarcinoma pathology images. MSNet is designed to efficiently harness the valuable features within data patches, while simultaneously reducing model complexity, computational demands, and storage space requirements. The MSNet framework employs a dual data stream input method. In this input method, MSNet combines Swin Transformer and MLP-Mixer models to address global information between patches and the local information within each patch. Subsequently, MSNet uses the Multilayer Perceptron (MLP) module to fuse local and global features and perform classification to output the final detection results. In addition, a dataset of lung adenocarcinoma pathology images containing three categories is created for training and testing the MSNet framework. Experimental results show that the diagnostic accuracy of MSNet for lung adenocarcinoma pathology images is 96.55 %. In summary, MSNet has high classification performance and shows effectiveness and potential in the classification of lung adenocarcinoma pathology images.

Nodule-CLIP: Lung nodule classification based on multi-modal contrastive learning.

The latest developments in deep learning have demonstrated the importance of CT medical imaging for the classification of pulmonary nodules. However, challenges remain in fully leveraging the relevant medical annotations of pulmonary nodules and distinguishing between the benign and malignant labels of adjacent nodules. Therefore, this paper proposes the Nodule-CLIP model, which deeply mines the potential relationship between CT images, complex attributes of lung nodules, and benign and malignant attributes of lung nodules through a comparative learning method, and optimizes the model in the image feature extraction network by using its similarities and differences to improve its ability to distinguish similar lung nodules. Firstly, we segment the 3D lung nodule information by U-Net to reduce the interference caused by the background of lung nodules and focus on the lung nodule images. Secondly, the image features, class features, and complex attribute features are aligned by contrastive learning and loss function in Nodule-CLIP to achieve lung nodule image optimization and improve classification ability. A series of testing and ablation experiments were conducted on the public dataset LIDC-IDRI, and the final benign and malignant classification rate was 90.6%, and the recall rate was 92.81%. The experimental results show the advantages of this method in terms of lung nodule classification as well as interpretability.

The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for Revision of the Classification of Residual Tumor After Resection for the Forthcoming (Ninth) Edition of the TNM Classification of Lung Cancer.

INTRODUCTION: The goal of surgical resection is to completely remove a cancer; it is useful to have a system to describe how well this was accomplished. This is captured by the residual tumor (R) classification, which is separate from the TNM classification that describes the anatomic extent of a cancer independent of treatment. The traditional R-classification designates as R0 a complete resection, as R1 a macroscopically complete resection but with microscopic tumor at the surgical margin, and as R2 a resection that leaves gross tumor behind. For lung cancer, an additional category encompasses situations in which the presence of residual tumor is uncertain. METHODS: This paper represents a comprehensive review of evidence regarding these R categories and the descriptors thereof, focusing on studies published after the year 2000 and with adjustment for potential confounders. RESULTS: Consistent discrimination between complete, uncertain, and incomplete resection is revealed with respect to overall survival. Evidence regarding specific descriptors is generally somewhat limited and only partially consistent; nevertheless, the data suggest retaining all descriptors but with clarifications to address ambiguities. CONCLUSION: On the basis of this review, the R-classification for the ninth edition of stage classification of lung cancer is proposed to retain the same overall framework and descriptors, with more precise definitions of descriptors. These refinements should facilitate application and further research.

The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for Revision of the TNM Stage Groups in the Forthcoming (Ninth) Edition of the TNM Classification for Lung Cancer.

INTRODUCTION: The TNM classification of lung cancer is periodically revised. The International Association for the Study of Lung Cancer collected and analyzed a new database to inform the forthcoming ninth edition of the TNM classification. The results are herewith presented. METHODS: After exclusions, 76,518 patients from a total of 124,581 registered patients were available for analyses: 58,193 with clinical stage, 39,192 with pathologic stage, and 62,611 with best stage NSCLC. The proposed new N2 subcategories (N2a, involvement of single ipsilateral mediastinal or subcarinal nodal station, and N2b, involvement of multiple ipsilateral mediastinal nodal stations with or without involvement of the subcarinal nodal station) and the new M1c subcategories (M1c1, multiple extrathoracic metastases in one organ system, and M1c2, multiple extrathoracic metastases in multiple organ systems) were considered in the survival analyses. Several potential stage groupings were evaluated, using multiple analyses, including recursive partitioning, assessment of homogeneity within and discrimination between potential groups, clinical and statistical significance of survival differences, multivariable regression, and broad assessment of generalizability. RESULTS: T1N1, T1N2a, and T3N2a subgroups are assigned to IIA, IIB, and IIIA stage groups, respectively. T2aN2b and T2bN2b subgroups are assigned to IIIB. M1c1 and M1c2 remain in stage group IVB. Analyses reveal consistent ordering, discrimination of prognosis, and broad generalizability of the proposed ninth edition stage classification of lung cancer. CONCLUSIONS: The proposed stages for the ninth edition TNM improve the granularity of nomenclature about anatomic extent that has benefits as treatment approaches become increasingly differentiated and complex.

The International Association for the Study of Lung Cancer (IASLC) Staging Project for Lung Cancer: Recommendation to Introduce Spread Through Air Spaces as a Histologic Descriptor in the Ninth Edition of the TNM Classification of Lung Cancer. Analysis of 4061 Pathologic Stage I NSCLC.

INTRODUCTION: Spread through air spaces (STAS) consists of lung cancer tumor cells that are identified beyond the edge of the main tumor in the surrounding alveolar parenchyma. It has been reported by meta-analyses to be an independent prognostic factor in the major histologic types of lung cancer, but its role in lung cancer staging is not established. METHODS: To assess the clinical importance of STAS in lung cancer staging, we evaluated 4061 surgically resected pathologic stage I R0 NSCLC collected from around the world in the International Association for the Study of Lung Cancer database. We focused on whether STAS could be a useful additional histologic descriptor to supplement the existing ones of visceral pleural invasion (VPI) and lymphovascular invasion (LVI). RESULTS: STAS was found in 930 of 4061 of the pathologic stage I NSCLC (22.9%). Patients with tumors exhibiting STAS had a significantly worse recurrence-free and overall survival in both univariate and multivariable analyses involving cohorts consisting of all NSCLC, specific histologic types (adenocarcinoma and other NSCLC), and extent of resection (lobar and sublobar). Interestingly, STAS was independent of VPI in all of these analyses. CONCLUSIONS: These data support our recommendation to include STAS as a histologic descriptor for the Ninth Edition of the TNM Classification of Lung Cancer. Hopefully, gathering these data in the coming years will facilitate a thorough analysis to better understand the relative impact of STAS, LVI, and VPI on lung cancer staging for the Tenth Edition TNM Stage Classification.

The International Association for the Study of Lung Cancer Staging Project for Lung Cancer: Proposals for the Revision of the M Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Lung Cancer.

INTRODUCTION: This study analyzed all metastatic categories of the current TNM classification of NSCLC to propose modifications of the M component in the next edition (ninth) of the classification. METHODS: A database of 124,581 patients diagnosed between 2011 and 2019 was established; of these, 14,937 with NSCLC in stages IVA to IVB were available for this analysis. Overall survival was calculated using the Kaplan-Meier method, and prognosis was assessed using multivariable-adjusted Cox proportional hazards regression. RESULTS: The eighth edition M categories revealed good discrimination in the ninth edition data set. Assessments revealed that an increasing number of metastatic lesions were associated with decreasing prognosis; because this seems to be a continuum and adjustment for confounders was not possible, no specific lesion number was deemed appropriate for stage classification. Among tumors involving multiple metastases, decreasing prognosis was found with an increasing number of organ systems involved. Multiple assessments, including after adjustment for potential confounders, revealed that M1c patients who had metastases to a single extrathoracic organ system were prognostically distinct from M1c patients who had involvement of multiple extrathoracic organ systems. CONCLUSIONS: These data validate the eighth edition M1a and M1b categories, which are recommended to be maintained. We propose the M1c category be divided into M1c1 (involvement of a single extrathoracic organ system) and M1c2 (involvement of multiple extrathoracic organ systems).

Classification of benign and malignant pulmonary nodule based on local-global hybrid network.

BACKGROUND: The accurate classification of pulmonary nodules has great application value in assisting doctors in diagnosing conditions and meeting clinical needs. However, the complexity and heterogeneity of pulmonary nodules make it difficult to extract valuable characteristics of pulmonary nodules, so it is still challenging to achieve high-accuracy classification of pulmonary nodules. OBJECTIVE: In this paper, we propose a local-global hybrid network (LGHNet) to jointly model local and global information to improve the classification ability of benign and malignant pulmonary nodules. METHODS: First, we introduce the multi-scale local (MSL) block, which splits the input tensor into multiple channel groups, utilizing dilated convolutions with different dilation rates and efficient channel attention to extract fine-grained local information at different scales. Secondly, we design the hybrid attention (HA) block to capture long-range dependencies in spatial and channel dimensions to enhance the representation of global features. RESULTS: Experiments are carried out on the publicly available LIDC-IDRI and LUNGx datasets, and the accuracy, sensitivity, precision, specificity, and area under the curve (AUC) of the LIDC-IDRI dataset are 94.42%, 94.25%, 93.05%, 92.87%, and 97.26%, respectively. The AUC on the LUNGx dataset was 79.26%. CONCLUSION: The above classification results are superior to the state-of-the-art methods, indicating that the network has better classification performance and generalization ability.